{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9987174005985464,
  "eval_steps": 500,
  "global_step": 73,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013681060282171868,
      "grad_norm": 7.548368406170154,
      "learning_rate": 0.0,
      "loss": 1.5136,
      "step": 1
    },
    {
      "epoch": 0.027362120564343735,
      "grad_norm": 7.827536257097371,
      "learning_rate": 6.666666666666667e-07,
      "loss": 1.4973,
      "step": 2
    },
    {
      "epoch": 0.041043180846515606,
      "grad_norm": 7.398147035041813,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 1.4526,
      "step": 3
    },
    {
      "epoch": 0.05472424112868747,
      "grad_norm": 6.621467563471504,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.3913,
      "step": 4
    },
    {
      "epoch": 0.06840530141085935,
      "grad_norm": 5.273700898837342,
      "learning_rate": 2.666666666666667e-06,
      "loss": 1.3428,
      "step": 5
    },
    {
      "epoch": 0.08208636169303121,
      "grad_norm": 3.9736038530372646,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.1501,
      "step": 6
    },
    {
      "epoch": 0.09576742197520308,
      "grad_norm": 3.5059552761650705,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.2428,
      "step": 7
    },
    {
      "epoch": 0.10944848225737494,
      "grad_norm": 3.6945698874338477,
      "learning_rate": 4.666666666666667e-06,
      "loss": 1.3626,
      "step": 8
    },
    {
      "epoch": 0.12312954253954682,
      "grad_norm": 2.9010276135864124,
      "learning_rate": 5.333333333333334e-06,
      "loss": 1.0364,
      "step": 9
    },
    {
      "epoch": 0.1368106028217187,
      "grad_norm": 3.6634274177297486,
      "learning_rate": 6e-06,
      "loss": 1.1989,
      "step": 10
    },
    {
      "epoch": 0.15049166310389056,
      "grad_norm": 3.3162811107208,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.074,
      "step": 11
    },
    {
      "epoch": 0.16417272338606242,
      "grad_norm": 3.4273757924875965,
      "learning_rate": 7.333333333333333e-06,
      "loss": 0.9367,
      "step": 12
    },
    {
      "epoch": 0.1778537836682343,
      "grad_norm": 3.712520280275751,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9526,
      "step": 13
    },
    {
      "epoch": 0.19153484395040615,
      "grad_norm": 3.489057750483782,
      "learning_rate": 8.666666666666668e-06,
      "loss": 1.124,
      "step": 14
    },
    {
      "epoch": 0.20521590423257802,
      "grad_norm": 2.588795249616481,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.8115,
      "step": 15
    },
    {
      "epoch": 0.21889696451474988,
      "grad_norm": 2.5083608844278915,
      "learning_rate": 1e-05,
      "loss": 0.8998,
      "step": 16
    },
    {
      "epoch": 0.23257802479692177,
      "grad_norm": 1.733597300225938,
      "learning_rate": 9.998562273265786e-06,
      "loss": 0.7702,
      "step": 17
    },
    {
      "epoch": 0.24625908507909364,
      "grad_norm": 1.91140737255229,
      "learning_rate": 9.994249919886402e-06,
      "loss": 0.8392,
      "step": 18
    },
    {
      "epoch": 0.2599401453612655,
      "grad_norm": 2.2610549095712646,
      "learning_rate": 9.98706541985615e-06,
      "loss": 0.9605,
      "step": 19
    },
    {
      "epoch": 0.2736212056434374,
      "grad_norm": 1.820469178389298,
      "learning_rate": 9.977012904914133e-06,
      "loss": 0.8495,
      "step": 20
    },
    {
      "epoch": 0.28730226592560926,
      "grad_norm": 1.8986542607595096,
      "learning_rate": 9.964098156168143e-06,
      "loss": 0.8255,
      "step": 21
    },
    {
      "epoch": 0.3009833262077811,
      "grad_norm": 1.8732046088429473,
      "learning_rate": 9.948328600769996e-06,
      "loss": 0.8314,
      "step": 22
    },
    {
      "epoch": 0.314664386489953,
      "grad_norm": 2.022587424257079,
      "learning_rate": 9.929713307644245e-06,
      "loss": 0.9394,
      "step": 23
    },
    {
      "epoch": 0.32834544677212485,
      "grad_norm": 2.185047520868034,
      "learning_rate": 9.908262982272724e-06,
      "loss": 0.9943,
      "step": 24
    },
    {
      "epoch": 0.3420265070542967,
      "grad_norm": 1.858153572034805,
      "learning_rate": 9.883989960537934e-06,
      "loss": 0.919,
      "step": 25
    },
    {
      "epoch": 0.3557075673364686,
      "grad_norm": 1.6533796703245207,
      "learning_rate": 9.85690820162878e-06,
      "loss": 0.9009,
      "step": 26
    },
    {
      "epoch": 0.36938862761864044,
      "grad_norm": 1.5392129172041236,
      "learning_rate": 9.827033280012783e-06,
      "loss": 0.8536,
      "step": 27
    },
    {
      "epoch": 0.3830696879008123,
      "grad_norm": 1.2934191579255045,
      "learning_rate": 9.794382376479334e-06,
      "loss": 0.7038,
      "step": 28
    },
    {
      "epoch": 0.39675074818298417,
      "grad_norm": 1.5922900609334563,
      "learning_rate": 9.7589742682592e-06,
      "loss": 0.8082,
      "step": 29
    },
    {
      "epoch": 0.41043180846515603,
      "grad_norm": 1.3349784246999898,
      "learning_rate": 9.720829318225897e-06,
      "loss": 0.7657,
      "step": 30
    },
    {
      "epoch": 0.4241128687473279,
      "grad_norm": 1.3968084241612435,
      "learning_rate": 9.6799694631852e-06,
      "loss": 0.7583,
      "step": 31
    },
    {
      "epoch": 0.43779392902949976,
      "grad_norm": 1.4438050306391899,
      "learning_rate": 9.63641820125949e-06,
      "loss": 0.8281,
      "step": 32
    },
    {
      "epoch": 0.4514749893116717,
      "grad_norm": 1.5653751821202764,
      "learning_rate": 9.590200578374198e-06,
      "loss": 0.8164,
      "step": 33
    },
    {
      "epoch": 0.46515604959384355,
      "grad_norm": 1.4428794862229695,
      "learning_rate": 9.541343173854128e-06,
      "loss": 0.7563,
      "step": 34
    },
    {
      "epoch": 0.4788371098760154,
      "grad_norm": 1.424184980221859,
      "learning_rate": 9.48987408513794e-06,
      "loss": 0.8012,
      "step": 35
    },
    {
      "epoch": 0.4925181701581873,
      "grad_norm": 1.4959423264612097,
      "learning_rate": 9.435822911619564e-06,
      "loss": 0.7733,
      "step": 36
    },
    {
      "epoch": 0.5061992304403591,
      "grad_norm": 1.5145765101418414,
      "learning_rate": 9.379220737625877e-06,
      "loss": 0.8185,
      "step": 37
    },
    {
      "epoch": 0.519880290722531,
      "grad_norm": 1.4205405113619893,
      "learning_rate": 9.320100114540382e-06,
      "loss": 0.7728,
      "step": 38
    },
    {
      "epoch": 0.5335613510047028,
      "grad_norm": 1.3618866165050287,
      "learning_rate": 9.258495042083222e-06,
      "loss": 0.7188,
      "step": 39
    },
    {
      "epoch": 0.5472424112868748,
      "grad_norm": 1.3210682200708475,
      "learning_rate": 9.19444094875825e-06,
      "loss": 0.7462,
      "step": 40
    },
    {
      "epoch": 0.5609234715690466,
      "grad_norm": 1.5209903146284076,
      "learning_rate": 9.127974671478432e-06,
      "loss": 0.8553,
      "step": 41
    },
    {
      "epoch": 0.5746045318512185,
      "grad_norm": 1.320169467583813,
      "learning_rate": 9.059134434381274e-06,
      "loss": 0.7292,
      "step": 42
    },
    {
      "epoch": 0.5882855921333904,
      "grad_norm": 1.3832163792888312,
      "learning_rate": 8.987959826846479e-06,
      "loss": 0.7342,
      "step": 43
    },
    {
      "epoch": 0.6019666524155622,
      "grad_norm": 1.3410523808663086,
      "learning_rate": 8.914491780728471e-06,
      "loss": 0.7135,
      "step": 44
    },
    {
      "epoch": 0.6156477126977341,
      "grad_norm": 1.7453570328171104,
      "learning_rate": 8.838772546816857e-06,
      "loss": 0.895,
      "step": 45
    },
    {
      "epoch": 0.629328772979906,
      "grad_norm": 1.3236234248181074,
      "learning_rate": 8.760845670538387e-06,
      "loss": 0.7094,
      "step": 46
    },
    {
      "epoch": 0.6430098332620778,
      "grad_norm": 1.3474642609149368,
      "learning_rate": 8.6807559669144e-06,
      "loss": 0.7463,
      "step": 47
    },
    {
      "epoch": 0.6566908935442497,
      "grad_norm": 1.3020601607506088,
      "learning_rate": 8.598549494788111e-06,
      "loss": 0.7731,
      "step": 48
    },
    {
      "epoch": 0.6703719538264216,
      "grad_norm": 1.5137293508647862,
      "learning_rate": 8.5142735303366e-06,
      "loss": 0.877,
      "step": 49
    },
    {
      "epoch": 0.6840530141085934,
      "grad_norm": 1.5403773102256209,
      "learning_rate": 8.427976539882725e-06,
      "loss": 0.8081,
      "step": 50
    },
    {
      "epoch": 0.6977340743907653,
      "grad_norm": 1.4219674838583494,
      "learning_rate": 8.339708152022586e-06,
      "loss": 0.7865,
      "step": 51
    },
    {
      "epoch": 0.7114151346729372,
      "grad_norm": 1.3635386118244723,
      "learning_rate": 8.24951912908459e-06,
      "loss": 0.7789,
      "step": 52
    },
    {
      "epoch": 0.725096194955109,
      "grad_norm": 1.2536175575645903,
      "learning_rate": 8.157461337936506e-06,
      "loss": 0.7167,
      "step": 53
    },
    {
      "epoch": 0.7387772552372809,
      "grad_norm": 1.399259576609449,
      "learning_rate": 8.063587720157298e-06,
      "loss": 0.7842,
      "step": 54
    },
    {
      "epoch": 0.7524583155194527,
      "grad_norm": 1.3669785990529744,
      "learning_rate": 7.967952261590936e-06,
      "loss": 0.8057,
      "step": 55
    },
    {
      "epoch": 0.7661393758016246,
      "grad_norm": 1.2116543523109478,
      "learning_rate": 7.870609961299627e-06,
      "loss": 0.71,
      "step": 56
    },
    {
      "epoch": 0.7798204360837965,
      "grad_norm": 1.496951541567372,
      "learning_rate": 7.771616799934372e-06,
      "loss": 0.9227,
      "step": 57
    },
    {
      "epoch": 0.7935014963659683,
      "grad_norm": 1.4409586905300167,
      "learning_rate": 7.67102970754101e-06,
      "loss": 0.7771,
      "step": 58
    },
    {
      "epoch": 0.8071825566481402,
      "grad_norm": 1.3689064689741741,
      "learning_rate": 7.568906530820281e-06,
      "loss": 0.7964,
      "step": 59
    },
    {
      "epoch": 0.8208636169303121,
      "grad_norm": 1.4659172981797304,
      "learning_rate": 7.465305999860728e-06,
      "loss": 0.7944,
      "step": 60
    },
    {
      "epoch": 0.8345446772124839,
      "grad_norm": 1.5394174805450438,
      "learning_rate": 7.360287694363566e-06,
      "loss": 0.8467,
      "step": 61
    },
    {
      "epoch": 0.8482257374946558,
      "grad_norm": 1.577909399946238,
      "learning_rate": 7.253912009378953e-06,
      "loss": 0.8211,
      "step": 62
    },
    {
      "epoch": 0.8619067977768277,
      "grad_norm": 1.1486399152909672,
      "learning_rate": 7.146240120573358e-06,
      "loss": 0.6165,
      "step": 63
    },
    {
      "epoch": 0.8755878580589995,
      "grad_norm": 1.3636010924515631,
      "learning_rate": 7.037333949048005e-06,
      "loss": 0.7381,
      "step": 64
    },
    {
      "epoch": 0.8892689183411714,
      "grad_norm": 1.275910605216143,
      "learning_rate": 6.927256125728624e-06,
      "loss": 0.7358,
      "step": 65
    },
    {
      "epoch": 0.9029499786233434,
      "grad_norm": 1.29369042675824,
      "learning_rate": 6.816069955346986e-06,
      "loss": 0.6921,
      "step": 66
    },
    {
      "epoch": 0.9166310389055152,
      "grad_norm": 1.4240273029942732,
      "learning_rate": 6.703839380034945e-06,
      "loss": 0.779,
      "step": 67
    },
    {
      "epoch": 0.9303120991876871,
      "grad_norm": 1.3292854453457577,
      "learning_rate": 6.590628942551909e-06,
      "loss": 0.7228,
      "step": 68
    },
    {
      "epoch": 0.943993159469859,
      "grad_norm": 1.496692141287322,
      "learning_rate": 6.476503749166903e-06,
      "loss": 0.8125,
      "step": 69
    },
    {
      "epoch": 0.9576742197520308,
      "grad_norm": 1.5176216507128955,
      "learning_rate": 6.36152943221656e-06,
      "loss": 0.8534,
      "step": 70
    },
    {
      "epoch": 0.9713552800342027,
      "grad_norm": 1.302742485236075,
      "learning_rate": 6.245772112360568e-06,
      "loss": 0.6825,
      "step": 71
    },
    {
      "epoch": 0.9850363403163745,
      "grad_norm": 1.6413121562783546,
      "learning_rate": 6.129298360556304e-06,
      "loss": 0.9217,
      "step": 72
    },
    {
      "epoch": 0.9987174005985464,
      "grad_norm": 1.3894377677004774,
      "learning_rate": 6.012175159774488e-06,
      "loss": 0.8585,
      "step": 73
    }
  ],
  "logging_steps": 1,
  "max_steps": 146,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 73,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9628983689216.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}